Netflix EDA

#importing packages

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)import seaborn as sns
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.graph_objects as go
from plotly.offline import init_notebook_mode, iplot

Load the data

#import data

df=pd.read_csv("netflix_titles.csv")
df.head()

	show_id	type	title	director	cast	country	date_added	release_year	rating	duration	listed_in	description
0	s1	Movie	Dick Johnson Is Dead	Kirsten Johnson	NaN	United States	September 25, 2021	2020	PG-13	90 min	Documentaries	As her father nears the end of his life, filmm...
1	s2	TV Show	Blood & Water	NaN	Ama Qamata, Khosi Ngema, Gail Mabalane, Thaban...	South Africa	September 24, 2021	2021	TV-MA	2 Seasons	International TV Shows, TV Dramas, TV Mysteries	After crossing paths at a party, a Cape Town t...
2	s3	TV Show	Ganglands	Julien Leclercq	Sami Bouajila, Tracy Gotoas, Samuel Jouy, Nabi...	NaN	September 24, 2021	2021	TV-MA	1 Season	Crime TV Shows, International TV Shows, TV Act...	To protect his family from a powerful drug lor...
3	s4	TV Show	Jailbirds New Orleans	NaN	NaN	NaN	September 24, 2021	2021	TV-MA	1 Season	Docuseries, Reality TV	Feuds, flirtations and toilet talk go down amo...
4	s5	TV Show	Kota Factory	NaN	Mayur More, Jitendra Kumar, Ranjan Raj, Alam K...	India	September 24, 2021	2021	TV-MA	2 Seasons	International TV Shows, Romantic TV Shows, TV ...	In a city of coaching centers known to train I...

#examine the data
df.count()

show_id         8807
type            8807
title           8807
director        6173
cast            7982
country         7976
date_added      8797
release_year    8807
rating          8803
duration        8804
listed_in       8807
description     8807
dtype: int64

Examining and Dealing With Missing Data

# Missing data

for i in df.columns:
    null_rate = df[i].isna().sum() / len(df) * 100 
    if null_rate > 0 :
        print("{} null rate: {}%".format(i,round(null_rate,2)))

director null rate: 29.91%
cast null rate: 9.37%
country null rate: 9.44%
date_added null rate: 0.11%
rating null rate: 0.05%
duration null rate: 0.03%

# Dealing with Missing Data

# replacing missing data with mode
df['country'] = df['country'].fillna(df['country'].mode()[0])

# replacing missing string data with appropriate labels
df['cast'].replace(np.nan, 'No Data',inplace  = True)
df['director'].replace(np.nan, 'No Data',inplace  = True)

# Dropping other NAs
df.dropna(inplace=True)

# Dropping Duplicates
df.drop_duplicates(inplace= True)

#dividing into shows and movies

showz=df[df['type']=='TV Show']
moviez=df[df['type']=='Movie']

sns.set(style="darkgrid")
sns.countplot(x="type", data=df, palette="Set3").set(title='Number of Content Divided by Type')
plt.show()

#examining release dates of shows

df1 = showz[['date_added']]
df1['year'] = df1['date_added'].apply(lambda x : x.split(', ')[-1])
df1['month'] = df1['date_added'].apply(lambda x : x.lstrip().split(' ')[0])

month_order = ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October', 'November', 'December'][::-1]
df = df1.groupby('year')['month'].value_counts().unstack().fillna(0)[month_order].T
plt.figure(figsize=(10, 7), dpi=200)
plt.pcolor(df, cmap='afmhot_r', edgecolors='white', linewidths=2) # heatmap
plt.xticks(np.arange(0.5, len(df.columns), 1), df.columns, fontsize=7, fontfamily='serif')
plt.yticks(np.arange(0.5, len(df.index), 1), df.index, fontsize=7, fontfamily='serif')

plt.title('Netflix Contents Update', fontsize=12, fontfamily='calibri', fontweight='bold', position=(0.20, 1.0+0.02))
cbar = plt.colorbar()

cbar.ax.tick_params(labelsize=8) 
cbar.ax.minorticks_on()
plt.show()

<ipython-input-8-c02f0ab80d67>:4: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

<ipython-input-8-c02f0ab80d67>:5: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

findfont: Font family ['calibri'] not found. Falling back to DejaVu Sans.

# Examining parental advising ratings of movies

plt.figure(figsize=(12,10))
sns.set(style="darkgrid")
sns.countplot(x="rating", data=moviez, palette="Set2", order=moviez['rating'].value_counts().index[0:15])
plt.show()

Examining Netflix by country

# Feature engineering

#Reuploading data

df=pd.read_csv("netflix_titles.csv")
# Replacements
df['country'] = df['country'].fillna(df['country'].mode()[0])
df['cast'].replace(np.nan, 'No Data',inplace  = True)
df['director'].replace(np.nan, 'No Data',inplace  = True)
# Drops
df.dropna(inplace=True)
# Drop Duplicates
df.drop_duplicates(inplace= True)
# Helper column for various plots
df['count'] = 1

# Grabbing the first country mentioned for production

df['first_country'] = df['country'].apply(lambda x: x.split(",")[0])
df['first_country'].head()

# Updating Rating ages

ratings_ages = {
    'TV-PG': 'Older Kids',
    'TV-MA': 'Adults',
    'TV-Y7-FV': 'Older Kids',
    'TV-Y7': 'Older Kids',
    'TV-14': 'Teens',
    'R': 'Adults',
    'TV-Y': 'Kids',
    'NR': 'Adults',
    'PG-13': 'Teens',
    'TV-G': 'Kids',
    'PG': 'Older Kids',
    'G': 'Kids',
    'UR': 'Adults',
    'NC-17': 'Adults'
}

df['target_ages'] = df['rating'].replace(ratings_ages)
df['target_ages'].unique()

# Genre

df['genre'] = df['listed_in'].apply(lambda x :  x.replace(' ,',',').replace(', ',',').split(',')) 

# Reducing name length

df['first_country'].replace('United States', 'USA', inplace=True)
df['first_country'].replace('United Kingdom', 'UK',inplace=True)
df['first_country'].replace('South Korea', 'S. Korea',inplace=True)

# Creating a map showing content creation locations

country_codes = {'afghanistan': 'AFG',
 'albania': 'ALB',
 'algeria': 'DZA',
 'american samoa': 'ASM',
 'andorra': 'AND',
 'angola': 'AGO',
 'anguilla': 'AIA',
 'antigua and barbuda': 'ATG',
 'argentina': 'ARG',
 'armenia': 'ARM',
 'aruba': 'ABW',
 'australia': 'AUS',
 'austria': 'AUT',
 'azerbaijan': 'AZE',
 'bahamas': 'BHM',
 'bahrain': 'BHR',
 'bangladesh': 'BGD',
 'barbados': 'BRB',
 'belarus': 'BLR',
 'belgium': 'BEL',
 'belize': 'BLZ',
 'benin': 'BEN',
 'bermuda': 'BMU',
 'bhutan': 'BTN',
 'bolivia': 'BOL',
 'bosnia and herzegovina': 'BIH',
 'botswana': 'BWA',
 'brazil': 'BRA',
 'british virgin islands': 'VGB',
 'brunei': 'BRN',
 'bulgaria': 'BGR',
 'burkina faso': 'BFA',
 'burma': 'MMR',
 'burundi': 'BDI',
 'cabo verde': 'CPV',
 'cambodia': 'KHM',
 'cameroon': 'CMR',
 'canada': 'CAN',
 'cayman islands': 'CYM',
 'central african republic': 'CAF',
 'chad': 'TCD',
 'chile': 'CHL',
 'china': 'CHN',
 'colombia': 'COL',
 'comoros': 'COM',
 'congo democratic': 'COD',
 'Congo republic': 'COG',
 'cook islands': 'COK',
 'costa rica': 'CRI',
 "cote d'ivoire": 'CIV',
 'croatia': 'HRV',
 'cuba': 'CUB',
 'curacao': 'CUW',
 'cyprus': 'CYP',
 'czech republic': 'CZE',
 'denmark': 'DNK',
 'djibouti': 'DJI',
 'dominica': 'DMA',
 'dominican republic': 'DOM',
 'ecuador': 'ECU',
 'egypt': 'EGY',
 'el salvador': 'SLV',
 'equatorial guinea': 'GNQ',
 'eritrea': 'ERI',
 'estonia': 'EST',
 'ethiopia': 'ETH',
 'falkland islands': 'FLK',
 'faroe islands': 'FRO',
 'fiji': 'FJI',
 'finland': 'FIN',
 'france': 'FRA',
 'french polynesia': 'PYF',
 'gabon': 'GAB',
 'gambia, the': 'GMB',
 'georgia': 'GEO',
 'germany': 'DEU',
 'ghana': 'GHA',
 'gibraltar': 'GIB',
 'greece': 'GRC',
 'greenland': 'GRL',
 'grenada': 'GRD',
 'guam': 'GUM',
 'guatemala': 'GTM',
 'guernsey': 'GGY',
 'guinea-bissau': 'GNB',
 'guinea': 'GIN',
 'guyana': 'GUY',
 'haiti': 'HTI',
 'honduras': 'HND',
 'hong kong': 'HKG',
 'hungary': 'HUN',
 'iceland': 'ISL',
 'india': 'IND',
 'indonesia': 'IDN',
 'iran': 'IRN',
 'iraq': 'IRQ',
 'ireland': 'IRL',
 'isle of man': 'IMN',
 'israel': 'ISR',
 'italy': 'ITA',
 'jamaica': 'JAM',
 'japan': 'JPN',
 'jersey': 'JEY',
 'jordan': 'JOR',
 'kazakhstan': 'KAZ',
 'kenya': 'KEN',
 'kiribati': 'KIR',
 'north korea': 'PRK',
 'south korea': 'KOR',
 'kosovo': 'KSV',
 'kuwait': 'KWT',
 'kyrgyzstan': 'KGZ',
 'laos': 'LAO',
 'latvia': 'LVA',
 'lebanon': 'LBN',
 'lesotho': 'LSO',
 'liberia': 'LBR',
 'libya': 'LBY',
 'liechtenstein': 'LIE',
 'lithuania': 'LTU',
 'luxembourg': 'LUX',
 'macau': 'MAC',
 'macedonia': 'MKD',
 'madagascar': 'MDG',
 'malawi': 'MWI',
 'malaysia': 'MYS',
 'maldives': 'MDV',
 'mali': 'MLI',
 'malta': 'MLT',
 'marshall islands': 'MHL',
 'mauritania': 'MRT',
 'mauritius': 'MUS',
 'mexico': 'MEX',
 'micronesia': 'FSM',
 'moldova': 'MDA',
 'monaco': 'MCO',
 'mongolia': 'MNG',
 'montenegro': 'MNE',
 'morocco': 'MAR',
 'mozambique': 'MOZ',
 'namibia': 'NAM',
 'nepal': 'NPL',
 'netherlands': 'NLD',
 'new caledonia': 'NCL',
 'new zealand': 'NZL',
 'nicaragua': 'NIC',
 'nigeria': 'NGA',
 'niger': 'NER',
 'niue': 'NIU',
 'northern mariana islands': 'MNP',
 'norway': 'NOR',
 'oman': 'OMN',
 'pakistan': 'PAK',
 'palau': 'PLW',
 'panama': 'PAN',
 'papua new guinea': 'PNG',
 'paraguay': 'PRY',
 'peru': 'PER',
 'philippines': 'PHL',
 'poland': 'POL',
 'portugal': 'PRT',
 'puerto rico': 'PRI',
 'qatar': 'QAT',
 'romania': 'ROU',
 'russia': 'RUS',
 'rwanda': 'RWA',
 'saint kitts and nevis': 'KNA',
 'saint lucia': 'LCA',
 'saint martin': 'MAF',
 'saint pierre and miquelon': 'SPM',
 'saint vincent and the grenadines': 'VCT',
 'samoa': 'WSM',
 'san marino': 'SMR',
 'sao tome and principe': 'STP',
 'saudi arabia': 'SAU',
 'senegal': 'SEN',
 'serbia': 'SRB',
 'seychelles': 'SYC',
 'sierra leone': 'SLE',
 'singapore': 'SGP',
 'sint maarten': 'SXM',
 'slovakia': 'SVK',
 'slovenia': 'SVN',
 'solomon islands': 'SLB',
 'somalia': 'SOM',
 'south africa': 'ZAF',
 'south sudan': 'SSD',
 'spain': 'ESP',
 'sri lanka': 'LKA',
 'sudan': 'SDN',
 'suriname': 'SUR',
 'swaziland': 'SWZ',
 'sweden': 'SWE',
 'switzerland': 'CHE',
 'syria': 'SYR',
 'taiwan': 'TWN',
 'tajikistan': 'TJK',
 'tanzania': 'TZA',
 'thailand': 'THA',
 'timor-leste': 'TLS',
 'togo': 'TGO',
 'tonga': 'TON',
 'trinidad and tobago': 'TTO',
 'tunisia': 'TUN',
 'turkey': 'TUR',
 'turkmenistan': 'TKM',
 'tuvalu': 'TUV',
 'uganda': 'UGA',
 'ukraine': 'UKR',
 'united arab emirates': 'ARE',
 'united kingdom': 'GBR',
 'united states': 'USA',
 'uruguay': 'URY',
 'uzbekistan': 'UZB',
 'vanuatu': 'VUT',
 'venezuela': 'VEN',
 'vietnam': 'VNM',
 'virgin islands': 'VGB',
 'west bank': 'WBG',
 'yemen': 'YEM',
 'zambia': 'ZMB',
 'zimbabwe': 'ZWE'}

## countries 
from collections import Counter
colorscale = ["#f7fbff", "#ebf3fb", "#deebf7", "#d2e3f3", "#c6dbef", "#b3d2e9", "#9ecae1",
    "#85bcdb", "#6baed6", "#57a0ce", "#4292c6", "#3082be", "#2171b5", "#1361a9",
    "#08519c", "#0b4083", "#08306b"
]
    
def geoplot(ddf):
    country_with_code, country = {}, {}
    shows_countries = ", ".join(ddf['country'].dropna()).split(", ")
    for c,v in dict(Counter(shows_countries)).items():
        code = ""
        if c.lower() in country_codes:
            code = country_codes[c.lower()]
        country_with_code[code] = v
        country[c] = v

    data = [dict(
            type = 'choropleth',
            locations = list(country_with_code.keys()),
            z = list(country_with_code.values()),
            colorscale = [[0,"rgb(5, 10, 172)"],[0.65,"rgb(40, 60, 190)"],[0.75,"rgb(70, 100, 245)"],\
                        [0.80,"rgb(90, 120, 245)"],[0.9,"rgb(106, 137, 247)"],[1,"rgb(220, 220, 220)"]],
            autocolorscale = False,
            reversescale = True,
            marker = dict(
                line = dict (
                    color = 'gray',
                    width = 0.5
                ) ),
            colorbar = dict(
                autotick = False,
                title = ''),
          ) ]

    layout = dict(
        title = '',
        geo = dict(
            showframe = False,
            showcoastlines = False,
            projection = dict(
                type = 'Mercator'
            )
        )
    )

    fig = dict( data=data, layout=layout )
    iplot( fig, validate=False, filename='d3-world-map' )
    return country

country_vals = geoplot(df)
tabs = Counter(country_vals).most_common(25)

labels = [_[0] for _ in tabs][::-1]
values = [_[1] for _ in tabs][::-1]
trace1 = go.Bar(y=labels, x=values, orientation="h", name="", marker=dict(color="#a678de"))

data = [trace1]
layout = go.Layout(title="Countries with most content", height=700, legend=dict(x=0.1, y=1.1, orientation="h"))
fig = go.Figure(data, layout=layout)
fig.show()

#examining which countries produce most netflix content in a more quantitative form

data = df.groupby('first_country')['count'].sum().sort_values(ascending=False)[:10]

# Plot

color_map = ['#f5f5f1' for _ in range(10)]
color_map[0] = color_map[1] = color_map[2] =  '#b20710' # color highlight

fig, ax = plt.subplots(1,1, figsize=(12, 6))
ax.bar(data.index, data, width=0.5, 
       edgecolor='darkgray',
       linewidth=0.6,color=color_map)

#annotations
for i in data.index:
    ax.annotate(f"{data[i]}", 
                   xy=(i, data[i] + 150), #i like to change this to roughly 5% of the highest cat
                   va = 'center', ha='center',fontweight='light', fontfamily='serif')



# Remove border from plot

for s in ['top', 'left', 'right']:
    ax.spines[s].set_visible(False)
    
# Tick labels

ax.set_xticklabels(data.index, fontfamily='serif', rotation=0)

# Title and sub-title

fig.text(0.09, 1, 'Top 10 countries on Netflix', fontsize=15, fontweight='bold', fontfamily='serif')
fig.text(0.09, 0.95, 'The three most frequent countries have been highlighted.', fontsize=12, fontweight='light', fontfamily='serif')

fig.text(1.1, 1.01, 'Insight', fontsize=15, fontweight='bold', fontfamily='serif')

fig.text(1.1, 0.67, '''
Most Netflix content are produced in
the USA, India, and the UK.
'''
         , fontsize=12, fontweight='light', fontfamily='serif')

ax.grid(axis='y', linestyle='-', alpha=0.4)   

grid_y_ticks = np.arange(0, 4000, 500) # y ticks, min, max, then step
ax.set_yticks(grid_y_ticks)
ax.set_axisbelow(True)

#Axis labels

#plt.xlabel("Country", fontsize=12, fontweight='light', fontfamily='serif',loc='left',y=-1.5)
#plt.ylabel("Count", fontsize=12, fontweight='light', fontfamily='serif')
 #plt.legend(loc='upper right')
    
# thicken the bottom line if you want to
plt.axhline(y = 0, color = 'black', linewidth = 1.3, alpha = .7)

ax.tick_params(axis='both', which='major', labelsize=12)


import matplotlib.lines as lines
l1 = lines.Line2D([1, 1], [0, 1], transform=fig.transFigure, figure=fig,color='black',lw=0.2)
fig.lines.extend([l1])

ax.tick_params(axis=u'both', which=u'both',length=0)

plt.show()

<ipython-input-12-9084f6261040>:30: UserWarning:

FixedFormatter should only be used together with FixedLocator

#examining type of production by country

country_order = df['first_country'].value_counts()[:11].index
data_q2q3 = df[['type', 'first_country']].groupby('first_country')['type'].value_counts().unstack().loc[country_order]
data_q2q3['sum'] = data_q2q3.sum(axis=1)
data_q2q3_ratio = (data_q2q3.T / data_q2q3['sum']).T[['Movie', 'TV Show']].sort_values(by='Movie',ascending=False)[::-1]




###
fig, ax = plt.subplots(1,1,figsize=(15, 8),)

ax.barh(data_q2q3_ratio.index, data_q2q3_ratio['Movie'], 
        color='#b20710', alpha=0.8, label='Movie')
ax.barh(data_q2q3_ratio.index, data_q2q3_ratio['TV Show'], left=data_q2q3_ratio['Movie'], 
        color='#221f1f', alpha=0.8, label='TV Show')


ax.set_xlim(0, 1)
ax.set_xticks([])
ax.set_yticklabels(data_q2q3_ratio.index, fontfamily='serif', fontsize=11)

# male percentage
for i in data_q2q3_ratio.index:
    ax.annotate(f"{data_q2q3_ratio['Movie'][i]*100:.3}%", 
                   xy=(data_q2q3_ratio['Movie'][i]/2, i),
                   va = 'center', ha='center',fontsize=12, fontweight='light', fontfamily='serif',
                   color='white')

for i in data_q2q3_ratio.index:
    ax.annotate(f"{data_q2q3_ratio['TV Show'][i]*100:.3}%", 
                   xy=(data_q2q3_ratio['Movie'][i]+data_q2q3_ratio['TV Show'][i]/2, i),
                   va = 'center', ha='center',fontsize=12, fontweight='light', fontfamily='serif',
                   color='white')
    

fig.text(0.13, 0.93, 'Top 10 countries Movie & TV Show split', fontsize=15, fontweight='bold', fontfamily='serif')   
fig.text(0.131, 0.89, 'Percent Stacked Bar Chart', fontsize=12,fontfamily='serif')   

for s in ['top', 'left', 'right', 'bottom']:
    ax.spines[s].set_visible(False)
    
#ax.legend(loc='lower center', ncol=3, bbox_to_anchor=(0.5, -0.06))

fig.text(0.75,0.9,"Movie", fontweight="bold", fontfamily='serif', fontsize=15, color='#b20710')
fig.text(0.81,0.9,"|", fontweight="bold", fontfamily='serif', fontsize=15, color='black')
fig.text(0.82,0.9,"TV Show", fontweight="bold", fontfamily='serif', fontsize=15, color='#221f1f')


fig.text(1.1, 0.93, 'Insight', fontsize=15, fontweight='bold', fontfamily='serif')

fig.text(1.1, 0.44, '''
Netflix in India
is made up nearly entirely of Movies. 

South Korean Netflix on the other hand is 
almost entirely TV Shows.
'''
         , fontsize=12, fontweight='light', fontfamily='serif')



import matplotlib.lines as lines
l1 = lines.Line2D([1, 1], [0, 1], transform=fig.transFigure, figure=fig,color='black',lw=0.2)
fig.lines.extend([l1])




ax.tick_params(axis='both', which='major', labelsize=12)
ax.tick_params(axis=u'both', which=u'both',length=0)

plt.show()

<ipython-input-13-a3d6c36ae73b>:22: UserWarning:

FixedFormatter should only be used together with FixedLocator